一种新的雷达目标HRRP识别方法
|
摘要
针对雷达目标回波的非平稳特性,推导了S变换及其快速实现算法,利用电磁场时域有限差分算法仿真了3种军用飞机的宽带散射信号,采用S变换对飞机目标的雷达回波进行时频分析,提取时频分布图的矩特征作为目标特征矢量,利用改进径向基函数神经网络对特征矢量进行训练和学习,最后对3种飞机作了分类识别,取得了很好的识别效果。
Radar wideband scattering echoes of three kinds of fighters are obtained by using the method of finite difference time domain(FDTD).The principle and algorithm procedure of S transform are educed.We introduce a new approach of feature extraction based on moments of the S transform time-frequency matrix of the echoes.The RBFNN is employed as the classifier,and the experimental results show that the new method is available and effective.
Radar wideband scattering echoes of three kinds of fighters are obtained by using the method of finite difference time domain(FDTD).The principle and algorithm procedure of S transform are educed.We introduce a new approach of feature extraction based on moments of the S transform time-frequency matrix of the echoes.The RBFNN is employed as the classifier,and the experimental results show that the new method is available and effective.
引文
[1]Stockwell R G,Mansinha L,Lowe R P.Localizationof the Complex Spectrum:The S Transform[J].IEEETrans on Signal Processing,1996,44(4):998-1001.
[2]Pinnegar C R,Mansinha L.Ti me-Local Spectral Anal-ysis for Non-Stationary Ti me Series:The S-Transformfor Noisy Signals[J].Fluctuation and Noise Letters,2003,3(3):357-364.
[3]陈学华,贺振华.改进的S变换及在地震信号处理中的应用[J].数据采集与处理,2005,20(4):449-453.CHEN Xue-hua,HE Zhen-hua.I mproved S-Trans-form and Its Application in Seismic Signal Processing[J].Journal of Data Acquisition&Processing,2005,20(4):449-453.(in Chinese)
[4]ChoHuak Teh,Roland T Chin.On I mage Analysis bythe Methods of Moments[J].IEEE Trans on PAMI,1988,10(4):496-513.
[5]鲜明,庄钊文,郭桂蓉,等.基于时频分析的飞机目标识别[J].国防科技大学学报,1997,19(3):9-13.Xian Ming,Zhuang Zhaowen,Guo Guirong,et al.Targets Recognition Based on Ti me-Frequency Analy-sis[J].Journal of National University of DefenseTechnology,1997,19(3):9-13.(in Chinese)
[6]刘宏伟,保铮.基于复合特征及分层特征选择的雷达HRRP识别[J].系统工程与电子技术,2005,27(4):596-599.LI U Hong-wei,BAO Zheng.Radar HRRP Recogni-tion Based on Hybrid Features and Multi-Stage Fea-ture Selection Scheme[J].Systems Engineering andElectronics,2005,27(4):596-599.(in Chinese)
[7]Assous S,Humeau A,L huillier J P.S-TransformTi me-Frequency Feature Extraction of Laser DopplerFlowmetry Signal Using SVD Decomposition[C]∥IEEEICASSP,Toulouse:[s.n.],2006.
[2]Pinnegar C R,Mansinha L.Ti me-Local Spectral Anal-ysis for Non-Stationary Ti me Series:The S-Transformfor Noisy Signals[J].Fluctuation and Noise Letters,2003,3(3):357-364.
[3]陈学华,贺振华.改进的S变换及在地震信号处理中的应用[J].数据采集与处理,2005,20(4):449-453.CHEN Xue-hua,HE Zhen-hua.I mproved S-Trans-form and Its Application in Seismic Signal Processing[J].Journal of Data Acquisition&Processing,2005,20(4):449-453.(in Chinese)
[4]ChoHuak Teh,Roland T Chin.On I mage Analysis bythe Methods of Moments[J].IEEE Trans on PAMI,1988,10(4):496-513.
[5]鲜明,庄钊文,郭桂蓉,等.基于时频分析的飞机目标识别[J].国防科技大学学报,1997,19(3):9-13.Xian Ming,Zhuang Zhaowen,Guo Guirong,et al.Targets Recognition Based on Ti me-Frequency Analy-sis[J].Journal of National University of DefenseTechnology,1997,19(3):9-13.(in Chinese)
[6]刘宏伟,保铮.基于复合特征及分层特征选择的雷达HRRP识别[J].系统工程与电子技术,2005,27(4):596-599.LI U Hong-wei,BAO Zheng.Radar HRRP Recogni-tion Based on Hybrid Features and Multi-Stage Fea-ture Selection Scheme[J].Systems Engineering andElectronics,2005,27(4):596-599.(in Chinese)
[7]Assous S,Humeau A,L huillier J P.S-TransformTi me-Frequency Feature Extraction of Laser DopplerFlowmetry Signal Using SVD Decomposition[C]∥IEEEICASSP,Toulouse:[s.n.],2006.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心